• 방송공학회논문지
• /
• 제21권1호
• /
• pp.87-96
• /
• 2016

최근 웹 또는 모바일 기기에서 전자지도를 이용한 정보 제공 서비스의 활성화로 도로 노면의 다양한 기호들을 자동으로 인식하는 기술이 요구되고 있다. 본 논문에서는 HOG-SP(Histogram of oriented Gradients-Split Projection) 서술자를 이용하여 도로 노면에 표시된 11가지의 방향지시기호를 자동으로 인식하는 방법을 제안하였으며, 인식된 방향지시기호를 기반으로 차선 위치 검출의 성능 향상을 나타내었다. 네이버 로드 뷰 영상으로 실험하여 제안하는 방법으로 81.99%의 인식률을 보였으며, 기존의 다른 특징들과의 비교 실험을 통해 제안하는 방법의 우수성을 입증하였다. 또한, 방향지시기호를 먼저 인식한 후 차선의 위치를 검출함으로써 단순히 차선의 위치만 검출하는 방법보다 7.64% 더 높은 검출률을 얻었다.

• 대한전자공학회논문지SP
• /
• 제48권2호
• /
• pp.96-101
• /
• 2011

소실점이란 실제 공간의 평행한 선들이 영상 내에 투영되면서 한곳에 모이는 점이다. 본 논문에서는 이러한 소실점의 특성을 이용한 실시간 소실점 검출 알고리즘을 제안한다. 기존의 소실점 검출 방법은 1) 복잡한 계산이 요구되거나 2) 알고리즘에 따라 소실점을 검출할 수 있는 영상이 제한되어 있다. 제안하는 방법은 블록 기반의 HOG(Histogram of Oriented Gradient)를 구하여 영상의 구조적 특성을 이용하는 것으로 영상 내에 존재하는 소실점을 실시간으로 검출한다. 먼저 영상의 블록 단위로 HOG 기술자를 구한 뒤, 제안하는 동적 프로그래밍(dynamic programing)을 이용하여 소실점의 위치를 예측한다. 본 논문에서는 다양한 영상에 대한 실험을 통해 제안하는 알고리즘이 효율적인 소실점 검출 방법임을 보이고자 한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권11호
• /
• pp.5436-5458
• /
• 2017

Automatic Video Surveillance System (AVSS) has become important to computer vision researchers as crime has increased in the twenty-first century. As a new branch of AVSS, baggage detection has a wide area of security applications. Some of them are, detecting baggage in baggage restricted super shop, detecting unclaimed baggage in public space etc. However, in this paper, a detection & classification framework of baggage is proposed. Initially, background subtraction is performed instead of sliding window approach to speed up the system and HSI model is used to deal with different illumination conditions. Then, a model is introduced to overcome shadow effect. Then, occlusion of objects is detected using proposed mirroring algorithm to track individual objects. Extraction of rotational signal descriptor (SP-RSD-HOG) with support plane from Region of Interest (ROI) add rotation invariance nature in HOG. Finally, dynamic human body parameter setting approach enables the system to detect & classify single or multiple pieces of carried baggage even if some portions of human are absent. In baggage detection, a strong classifier is generated by boosting similarity measure based multi layer Support Vector Machine (SVM)s into HOG based SVM. This boosting technique has been used to deal with various texture patterns of baggage. Experimental results have discovered the system satisfactorily accurate and faster comparative to other alternatives.

• Journal of Microbiology and Biotechnology
• /
• 제5권3호
• /
• pp.154-157
• /
• 1995

MRK-22, an inhibitor of aminopeptidase M was isolated from the culture broth of Streptomyces sp. SL20209. The structure of MRK-22 was defined to be 3-amino-2-hydroxy-5-methylhexanoyl-valyl-valine, des-$Asp^4$-amastatin, by spectroscopic analysis and this was also confirmed by solid phase synthesis of the inhibitor. The molecular formula and weight of MRK-22 were $C_17H_33N_3O_5$ and MW 359($M^+$), respectively, and its $IC_50$ value against hog kidney AP-M was 0.79 $\mu$ g/ml.

• Journal of Microbiology and Biotechnology
• /
• 제5권1호
• /
• pp.36-40
• /
• 1995

Valistatin, a new inhibitor of aminopeptidase M(AP-M) was discovered in the culture broth of Streptomyces sp. SL20209 isolated from a soil sample. The inhibitor was purified by extraction with n-butanol and the various column chromatographies, and then isolated as whitish powder. The $^1 H-and ^1 H, ^1 H-COSY$ NMR studies, amino acid analysis, and fragmentation patterns by FAB-MS suggested the presence of one 3-amino-2-hydroxy-4-phenylbutanoic acid and two valine residues in the inhibitor. Thus, the structure of valistatin was determined as 3-amino-2-hydroxy-4-phenylbutanoyl-valyl-valine. Valistatin has the molecular formular $C_20H_31N_3 O_5$ (MW 394), and its $IC_50$ value against hog kidney AP-M was determined to be 3.12 $mu g/ml$.

• 한국미생물·생명공학회지
• /
• 제10권4호
• /
• pp.283-288
• /
• 1982

Streptomyces속 균이 생산하는 trypsin inhibitor의 trypsin에 대한 반응성을 조사해 본 결과 본 저해물질은 crystalline trypsin (20.000 unit, hog pancreas)에 대하여 1/8량에서 약 50%의 저해률을 나타내었으며 trypsin에 대한 저해양상은 mixed noncompetitive-competitive inhibition type이었으며 enzyme-inhibitor complex를 빨리 형성하는데 반응액중 isoleucine이 공존하면 활성이 증가되였으며 Ag$_{＋}$ Hg$_{＋＋}$등의 금속ion은 강하게 본 저해물질의 작용을 억제하였다. 저해률은 사용한 기질의 종류에 따라 차이가 나서 albumin을 사용하였을 때는 casein이나 hemoglobin을 사용하였을 때보다 저해률이 높았다. 그러고 혈액의 응고에 대해서도 저해작용을 나타내었다.

• Asian-Australasian Journal of Animal Sciences
• /
• 제17권2호
• /
• pp.199-202
• /
• 2004

Cellulolytic bacterial strains have been isolated from the faeces of wild (blackbuck, Antilope cervicapra; nilgai, Baselophus tragocamelus chinkara, Gazella gazella spotted deer, Axis axis and hog deer, Cervus porcinus) and rumen liquor of domestic (sheep, Ovis aries) ruminants. Five best cellulose degrading bacterial isolates (Ruminococcus sp.) were used as microbial feed additive along with buffalo rumen liquor as inoculum to study their effect on digestibility of feed and enzyme production in in vitro conditions. The bacterial isolate from chinkara (CHI-2) showed the highest per cent apparent dry matter (DM) digestibility ($35.40{\pm}0.60$), true dry matter digestibility ($40.80{\pm}0.69$) and NDF ($26.38{\pm}0.83$) digestibility (p<0.05) compared to control ($32.73{\pm}0.56$, $36.64{\pm}0.71$ and $21.16{\pm}0.89$, respectively) and other isolates at 24 h of incubation with lignocellulosic feeds (wheat straw and wheat bran, 80:20). The same isolate also exhibited the highest activities of fibre degrading enzymes like carboxymethylcellulase, xylanase, ${\beta}$-glucosidase and acetyl esterase. The bacterial isolate from chinkara (Gazella gazella) appears to have a potential to be used as feed additive in the diet of ruminants for improving utilization of nutrients from lignocellulosic feeds.